Evolving Differentiable Gene Regulatory Networks
This work addresses the usability of GRNs in machine learning, offering an incremental improvement for researchers in evolutionary computation and bio-inspired AI.
The paper tackles the problem of optimizing Gene Regulatory Networks (GRNs) for machine learning applications by introducing a GPU-based differentiable implementation that enables local optimization with stochastic gradient descent (SGD). The result shows that combining evolution and SGD can improve GRN optimization, as evaluated on a standard dataset, though no concrete numbers are provided.
Over the past twenty years, artificial Gene Regulatory Networks (GRNs) have shown their capacity to solve real-world problems in various domains such as agent control, signal processing and artificial life experiments. They have also benefited from new evolutionary approaches and improvements to dynamic which have increased their optimization efficiency. In this paper, we present an additional step toward their usability in machine learning applications. We detail an GPU-based implementation of differentiable GRNs, allowing for local optimization of GRN architectures with stochastic gradient descent (SGD). Using a standard machine learning dataset, we evaluate the ways in which evolution and SGD can be combined to further GRN optimization. We compare these approaches with neural network models trained by SGD and with support vector machines.